curius graph

all pages

showing 9701-9750 of 168680 pages (sorted by popularity)
Tiny Algae and the Political Theater of Planting One Trillion Trees
[2210.05337] SGD with large step sizes learns sparse features
Michael Nielsen on visualizations, biological systems, and making a new science
Shtetl-Optimized » Blog Archive » My AI Safety Lecture for UT Effective Altruism
innovative_contracting_case_studies_2014_-_august.pdf
12 tentative ideas for US AI policy - Open Philanthropy
Do Machine Learning Models Memorize or Generalize?
CaMeL offers a promising new direction for mitigating prompt injection attacks
Can we safely automate alignment research? - Joe Carlsmith
AI will not suddenly lead to an Alzheimer’s cure
Cyber Competitions
Discussing Learned Concepts with Language Models · John Hewitt
Proofs & Reasons @ CMU
The Engineering State - American Affairs Journal
Benchmark Scores = General Capability + Claudiness | Epoch AI
Ideas Aren’t Getting Harder to Find—Asterisk
How "Discovering Latent Knowledge in Language Models Without Supervision" Fits Into a Broader Alignment Scheme — LessWrong
A starting point for making sense of task structure (in machine learning) — LessWrong
Efficient Dictionary Learning with Switch Sparse Autoencoders — LessWrong
DSLT 1. The RLCT Measures the Effective Dimension of Neural Networks — LessWrong
DSLT 1. The RLCT Measures the Effective Dimension of Neural Networks — LessWrong
Training a Reward Hacker Despite Perfect Labels — LessWrong
Plans A, B, C, and D for misalignment risk — LessWrong
13 Arguments About a Transition to Neuralese AIs — LessWrong
ARC progress update: Competing with sampling — LessWrong
[2511.00617] Belief Dynamics Reveal the Dual Nature of In-Context Learning and Activation Steering
Circuits Updates - April 2024
Insights into Claude Opus 4.5 from Pokémon — LessWrong
Dynamic context discovery · Cursor
The Quiet Evolution of the Venture Capital Industry
How I Got a Job at Google DeepMind (No ML Degree) | Medium
The Need to Read
Emergence - Wikipedia
Particle swarm optimization - Wikipedia
The Rise of Computer Use and Agentic Coworkers | Andreessen Horowitz
Letters to a Young Investor: Mike Maples, Jr.
Forget "GPT-Wrappers": The Future of AI Startups is Last-Mile Delivery
2014-04-08-dare-to-be-great-ii.pdf
2412.12480
Deep Deceptiveness — LessWrong
Neuroscience of human social instincts: a sketch — LessWrong
Home | LawZero
Introducing SB53.info
Saying Goodbye — LessWrong
The Problem — LessWrong
Claude is a Ravenclaw — LessWrong
Trust me bro, just one more RL scale up, this one will be the real scale up with the good environments, the actually legit one, trust me bro
Does Reality Drive Straight Lines On Graphs, Or Do Straight Lines On Graphs Drive Reality? | Slate Star Codex
Untitled
On Pessimization - by Richard Ngo - Mind the Future